Home
Uni-Logo
 

Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images

V. Golkov, M. Skwark, A. Golkov, Alexey Dosovitskiy, Thomas Brox, J. Meiler, D. Cremers
Advances in Neural Information Processing Systems (NIPS), 2016
Download the publication : p5.pdf [2.7Mo]  

Abstract: Proteins are responsible for most of the functions in life, and thus are the central focus of many areas of biomedicine. Protein structure is strongly related to protein function, but is difficult to elucidate experimentally, therefore computational structure prediction is a crucial task on the way to solve many biological questions. A contact map is a compact representation of the three-dimensional structure of a protein via the pairwise contacts between the amino acids constituting the protein. We use a convolutional network to calculate protein contact maps from detailed evolutionary coupling statistics between positions in the protein sequence. The input to the network has an image-like structure amenable to convolutions, but every "pixel" instead of color channels contains a bipartite undirected edge-weighted graph. We propose several methods for treating such "graph-valued images" in a convolutional network. The proposed method outperforms state-of-the-art methods by a considerable margin.

Images and movies

 

BibTex references

@InProceedings{DB16e,
  author       = "V. Golkov and M. J. Skwark and A. Golkov and A. Dosovitskiy and T. Brox and J. Meiler and D. Cremers",
  title        = "Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images",
  booktitle    = "Advances in Neural Information Processing Systems (NIPS)",
  month        = " ",
  year         = "2016",
  url          = "http://lmb.informatik.uni-freiburg.de//Publications/2016/DB16e"
}

Other publications in the database